#coding = utf-8;

import re;

import requests;

from datetime import datetime;

from bs4 import BeautifulSoup;

class News(object):

    '''

        广商校园新闻

    '''

    def __init__(self, url):

        self.url = url;             #新闻网页地址

        self._dom_tree = self._tranfrom_dom_tree(url);

        self._show_infos = self._dom_tree.select(".show-info")[0].text.split();

        self._update_time = self._show_infos[0][5:] + " " + self._show_infos[1];     # 最后更新时间

    def _tranfrom_dom_tree(self,url):

        '''

            将获取的html文本转化为dom树

        '''

        response = requests.get(url);

        response.encoding = "utf-8";

        return BeautifulSoup(response.text, "html.parser");

    # 新闻标题

    @property

    def title(self):

        return self._dom_tree.select(".show-title")[0].text;

    # 新闻作者

    @property

    def auothor(self):

        return self._show_infos[2][3:];

    # 新闻审核

    @property

    def auditor(self):

        return self._show_infos[3][3:];

    # 新闻发布单位

    @property

    def origin(self):

        self._show_infos[4][3:];

    # 新闻最后更新时间

    @property

    def update_time(self):

        return self._update_time;

    @update_time.setter

    def update_time(self, time):

        self._update_time = time;

    # 点击次数

    @property

    def times(self):

        clickUrl = 'http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80'.format(self.news_id);

        res = requests.get(clickUrl)

        click = re.findall('(\d+)', res.text)[-1]

        return click

    # 新闻标识

    @property

    def news_id(self):

        time = datetime.strptime(self._update_time, '%Y-%m-%d %H:%M:%S');

        time = time.strftime("%m%d");

        re.match('http://news.gzcc.cn/html/2019/.*/(\d+).html', self.url).group(1)

if __name__ == "__main__":

    html_url = "http://news.gzcc.cn/html/2019/xiaoyuanxinwen_0322/11047.html";

    news = News(html_url);